INDEX

Explanations

phrases related to crime, legal proceedings, and consequences

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

oras

-0.16

 Ø®Ø·Ø±

-0.16

 offender

-0.15

endon

-0.15

bstract

-0.14

á»Ńa

-0.14

extends

-0.14

ÙĬÙĩ

-0.14

 Marr

-0.14

umas

-0.14

POSITIVE LOGITS

 incident

0.26

incident

0.24

 events

0.20

 incidents

0.18

 Incident

0.18

 recent

0.17

 quadr

0.17

cu

0.16

 case

0.16

 Events

0.16

Activations Density 0.102%

phrases related to crime, legal proceedings, and consequences

No Comments

No Known Activations